© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 38409
    Prev
    Next
    INDEX
    Explanations

    simple but stuck

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ink
    -0.07
    .wik
    -0.07
    æľŁéĸĵ
    -0.07
    åıĬ产åĵģ
    -0.07
    å®ŀä½ĵ
    -0.07
    raw
    -0.06
    å¯Ĵæ°Ķ
    -0.06
    akor
    -0.06
    æľŁéĻIJ
    -0.06
     softer
    -0.06
    POSITIVE LOGITS
    ä¸įç®Ģåįķ
    0.10
    ä¸įå¹³åĩ¡
    0.09
    /simple
    0.09
    ç»ĨèĬĤ
    0.09
    -simple
    0.09
     simplicity
    0.09
     simple
    0.08
    ç®Ģåįķ
    0.08
     simples
    0.08
    éĩįå¤į
    0.08
    Activations Density 0.133%

    No Known Activations